{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:19:49Z","timestamp":1781194789327,"version":"3.54.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832332","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T13:31:27Z","timestamp":1737034287000},"page":"302-308","source":"Crossref","is-referenced-by-count":73,"title":["An Investigation of Incorporating Mamba For Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Rong","family":"Chao","sequence":"first","affiliation":[{"name":"Academia Sinica"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moreno La","family":"Quatra","sequence":"additional","affiliation":[{"name":"Kore University of Enna"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabato Marco","family":"Siniscalchi","sequence":"additional","affiliation":[{"name":"University of Palermo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao-Han Huck","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Szu-Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2017.7864754"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1159\/000094648"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2986896"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3426924"},{"key":"ref8","article-title":"D4AM: A general denoising framework for downstream acoustic models","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-574"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-659"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107347"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393718"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref19","article-title":"Explicit estimation of magnitude and phase spectra in parallel for high-quality speech enhancement","author":"Lu","year":"2023","journal-title":"arXiv preprint arXiv:2308.08926"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3016837"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref25","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. ICML","author":"Fu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328282"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10478"},{"key":"ref29","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv:2312.00752"},{"key":"ref30","article-title":"Dual-path mamba: Short and long-term bidirectional selective structured state space models for speech separation","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv:2403.18257"},{"key":"ref31","article-title":"Spmamba: State-space model is all you need in speech separation","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2404.02063"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2016-24"},{"key":"ref33","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. ICLR","author":"Gu"},{"key":"ref34","article-title":"On the parameterization and initialization of diagonal state space models","volume-title":"Proc. NeurIPS","author":"Gu"},{"key":"ref35","article-title":"Hungry hungry hippos: Towards language modeling with state space models","author":"Fu","year":"2022","journal-title":"arXiv preprint arXiv:2212.14052"},{"key":"ref36","article-title":"Boosting objective scores of a speech enhancement model by metricgan post-processing","volume-title":"Proc. APSIPA","author":"Fu"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2023-456","article-title":"SCP-GAN: Self-correcting discriminator optimization for training consistency preserving metric gan on speech enhancement tasks","volume-title":"arXiv:2210.14474","author":"Zadorozhnyy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3362691"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1084"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448152"},{"key":"ref45","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832332.pdf?arnumber=10832332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:40:54Z","timestamp":1769488854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832332","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}